{"id":"W4378419649","doi":"10.1007/978-3-031-33380-4_31","title":"RLMixer: A Reinforcement Learning Approach for Integrated Ranking with Contrastive User Preference Modeling","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Ranking (information retrieval); Computer science; Reinforcement learning; Preference; Recommender system; Metric (unit); Artificial intelligence; Revenue; Machine learning; Preference learning; Term (time); Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001424272,0.0006608316,0.0007634975,0.0008239417,0.0004186274,0.000822757,0.002462523,0.0003255433,0.000002250001],"category_scores_gemma":[0.00007929514,0.0005090485,0.0001394679,0.0006791761,0.0002346425,0.0006661381,0.0008369033,0.001041566,0.00000431219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003402206,"about_ca_system_score_gemma":0.0005268054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001024949,"about_ca_topic_score_gemma":0.00004962289,"domain_scores_codex":[0.9958162,0.00004962214,0.000675382,0.001743163,0.0008962726,0.0008193688],"domain_scores_gemma":[0.9975922,0.0004145821,0.0004028287,0.0008941377,0.0005533139,0.0001429656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002609512,0.00001439936,0.000023008,0.0001018192,0.00004159265,0.00001441407,0.001109246,0.8063121,0.00003341629,0.02878186,0.00001291307,0.1635291],"study_design_scores_gemma":[0.0004389267,0.0004129632,0.000002518319,0.0009808854,0.00001251095,0.00002974138,0.000001654174,0.9789057,0.00042122,0.01774905,0.0003986344,0.0006462296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000187696,0.00008967004,0.994487,0.0001147246,0.0004953709,0.001504936,0.000003119229,0.0006820837,0.002604281],"genre_scores_gemma":[0.3060609,0.00003573077,0.6921839,0.0002427629,0.0001938025,0.0002003798,0.00002765365,0.00007250869,0.0009823201],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3060422,"threshold_uncertainty_score":0.9997361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0475176102982988,"score_gpt":0.2490568989841326,"score_spread":0.2015392886858338,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}